CSpace

浏览/检索结果: 共29条,第1-10条 帮助

已选(0)清除 条数/页:   排序方式:
HiHGNN: Accelerating HGNNs Through Parallelism and Data Reusability Exploitation 期刊论文
IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS, 2024, 卷号: 35, 期号: 7, 页码: 1122-1138
作者:  Xue, Runzhen;  Han, Dengke;  Yan, Mingyu;  Zou, Mo;  Yang, Xiaocheng;  Wang, Duo;  Li, Wenming;  Tang, Zhimin;  Kim, John;  Ye, Xiaochun;  Fan, Dongrui
收藏  |  浏览/下载:1/0  |  提交时间:2024/12/06
Semantics  Parallel processing  Graph neural networks  Vectors  Graphics processing units  Fuses  Hardware  GNN  GNN accelerator  graph neural network  HGNN  HGNN accelerator  heterogeneous graph neural network  
MoDSE: A High-Accurate Multiobjective Design Space Exploration Framework for CPU Microarchitectures 期刊论文
IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS, 2024, 卷号: 43, 期号: 5, 页码: 1525-1537
作者:  Wang, Duo;  Yan, Mingyu;  Teng, Yihan;  Han, Dengke;  Liu, Xin;  Li, Wenming;  Ye, Xiaochun;  Fan, Dongrui
收藏  |  浏览/下载:3/0  |  提交时间:2024/12/06
Pareto optimization  Predictive models  Measurement  Space exploration  Prediction algorithms  Central Processing Unit  Microarchitecture  CPU microarchitecture  design space exploration (DSE)  multiobjective exploration  Pareto hypervolume  prediction model  
Characterizing and Understanding Defense Methods for GNNs on GPUs 期刊论文
IEEE COMPUTER ARCHITECTURE LETTERS, 2023, 卷号: 22, 期号: 2, 页码: 137-140
作者:  Wu, Meng;  Yan, Mingyu;  Yang, Xiaocheng;  Li, Wenming;  Zhang, Zhimin;  Ye, Xiaochun;  Fan, Dongrui
收藏  |  浏览/下载:17/0  |  提交时间:2023/12/04
Kernel  Purification  Estimation  Graphics processing units  Perturbation methods  Electric breakdown  Training  Graph neural networks  defense  execution semantic  execution pattern  overhead  
DRONE: An Efficient Distributed Subgraph-Centric Framework for Processing Large-Scale Power-law Graphs 期刊论文
IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS, 2023, 卷号: 34, 期号: 2, 页码: 463-474
作者:  Zhang, Shuai;  Jiang, Zite;  Hou, Xingzhong;  Li, Mingyu;  Yuan, Mengting;  You, Haihang
收藏  |  浏览/下载:23/0  |  提交时间:2023/07/12
Fault tolerance  graph partition  large-scale power-law graph  parallel graph computation  subgraph-centric model  
Multi-Node Acceleration for Large-Scale GCNs 期刊论文
IEEE TRANSACTIONS ON COMPUTERS, 2022, 卷号: 71, 期号: 12, 页码: 3140-3152
作者:  Sun, Gongjian;  Yan, Mingyu;  Wang, Duo;  Li, Han;  Li, Wenming;  Ye, Xiaochun;  Fan, Dongrui;  Xie, Yuan
收藏  |  浏览/下载:36/0  |  提交时间:2023/07/12
Deep learning  graph neural network  hardware accelerator  multi-node system  communication optimization  
Characterizing and Understanding HGNNs on GPUs 期刊论文
IEEE COMPUTER ARCHITECTURE LETTERS, 2022, 卷号: 21, 期号: 2, 页码: 69-72
作者:  Yan, Mingyu;  Zou, Mo;  Yang, Xiaocheng;  Li, Wenming;  Ye, Xiaochun;  Fan, Dongrui;  Xie, Yuan
收藏  |  浏览/下载:35/0  |  提交时间:2022/12/07
Kernel  Semantics  Aggregates  Mercury (metals)  Motion pictures  Graphics processing units  Electric breakdown  Heterogeneous graph neural networks  GNNs  characterization  execution semantic  execution pattern  
Sampling Methods for Efficient Training of Graph Convolutional Networks: A Survey 期刊论文
IEEE-CAA JOURNAL OF AUTOMATICA SINICA, 2022, 卷号: 9, 期号: 2, 页码: 205-234
作者:  Liu, Xin;  Yan, Mingyu;  Deng, Lei;  Li, Guoqi;  Ye, Xiaochun;  Fan, Dongrui
收藏  |  浏览/下载:38/0  |  提交时间:2022/06/21
Efficient training  graph convolutional networks (GCNs)  graph neural networks (GNNs)  sampling method  
Hardware Acceleration for GCNs via Bidirectional Fusion 期刊论文
IEEE COMPUTER ARCHITECTURE LETTERS, 2021, 卷号: 20, 期号: 1, 页码: 4
作者:  Li, Han;  Yan, Mingyu;  Yang, Xiaocheng;  Deng, Lei;  Li, Wenming;  Ye, Xiaochun;  Fan, Dongrui;  Xie, Yuan
收藏  |  浏览/下载:44/0  |  提交时间:2021/12/01
Random access memory  Computational modeling  Analytical models  Hardware  Engines  Computer architecture  Transforms  Graph convolutional neural networks  hardware accelerator  bidirectional execution  inter-phase fusion  
基于M/M/1排队模型的网络服务尾延迟分析 期刊论文
计算机科学, 2020, 卷号: 47, 期号: 11, 页码: 286
作者:  郭子亭;  张文力;  陈明宇
收藏  |  浏览/下载:11/0  |  提交时间:2024/05/20
Tail latency  Modeling  M/M/1  Series  Parallel  尾延迟  建模  M/M/1  串联  并行  
一种支持DDR4的软硬件结合的访存踪迹收集分析工具集 期刊论文
计算机工程与科学, 2019, 卷号: 41.0, 期号: 006, 页码: 973
作者:  李作骏;  陈明宇;  秦晓宁
收藏  |  浏览/下载:15/0  |  提交时间:2023/12/04
访存踪迹  FPGA  DDR4  物理地址